Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    drawings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Oxford
    -0.06
    GHz
    -0.06
    Monday
    -0.06
     ê
    -0.06
     yay
    -0.06
    chluss
    -0.06
    istle
    -0.06
    .delay
    -0.06
    Sphere
    -0.06
     ア
    -0.06
    POSITIVE LOGITS
     Appears
    0.07
     prostituerade
    0.06
     deduction
    0.06
    rections
    0.06
     squared
    0.06
    ross
    0.06
     ấn
    0.06
     Veg
    0.06
    수
    0.06
    incre
    0.06
    Act Density 0.001%

    No Known Activations